Get the latest tech news

StepFun 3.5 Flash is #1 cost-effective model for OpenClaw tasks (300 battles)


A public benchmark for evaluating whether AI agents can complete real workflows. Compare model performance and cost-effectiveness on real agent tasks.

None

Get the Android app

Or read this on Hacker News

Read more on:

Photo of cost

cost

Photo of battles

battles

Photo of OpenClaw

OpenClaw

Related news:

News photo

OpenClaw has 500,000 instances and no enterprise kill switch

News photo

The cost of physical Nintendo games is not going up, but we are going to start paying less for digital versions of its first-party titles

News photo

Show HN: Relay – The open-source Claude Cowork for OpenClaw